Few Shot Image Classification On Omniglot 5 1
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy |
|---|---|
| prototypical-networks-for-few-shot-learning | 98.9% |
| few-shot-learning-with-global-class | 99.32 |
| uncertainty-in-model-agnostic-meta-learning | 98.52% |
| learning-to-remember-rare-events | 98.6% |
| learning-to-compare-relation-network-for-few | 99.1% |
| matching-networks-for-one-shot-learning | 98.5% |
| decoder-choice-network-for-meta-learning | 99.63 |
| hyperbolic-image-embeddings | 98.15% |
| decoder-choice-network-for-meta-learning | 99.5% |
| on-first-order-meta-learning-algorithms | 97.12% |
| hypertransformer-model-generation-for | 99.3% |
| meta-learning-without-memorization-1 | 94.1% |
| rapid-adaptation-with-conditionally-shifted | 98.43% |
| tapnet-neural-network-augmented-with-task | 99.49% |
| meta-curvature | 99.65% |
| towards-a-neural-statistician | 98.1% |
| adaptive-posterior-learning-few-shot-learning | 97.6% |
| how-to-train-your-maml | 99.33% |
| meta-learning-with-implicit-gradients | 99.14% |